{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:02:53Z","timestamp":1785265373618,"version":"3.55.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"7","funder":[{"name":"National Human Genome Research Institute of the National Institutes of Health"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) is increasingly prevalent. Patients and clinicians may use AI-based tools in many different languages.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To investigate AI translation tools for descriptions of genetic conditions and how AI identification of genetic conditions is affected by translations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We used Neural machine translation (NMT) and large language-model (LLM) translation to translate descriptions of 40 genetic conditions into 191 and 93 languages, respectively. Excluding translations retaining English medical terms verbatim, we respectively focused on 139 and 70 languages. After assessing translations, we assessed the ability of 3 proprietary and 3 open-weight general LLMs to identify conditions in the translations. We analyzed how accuracy was affected by the conditions\u2019 prevalence in the literature, and attributes of the languages (the script, language family, and prevalence of the language in training sources). We also investigated adaptive translation for select languages.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We found significant differences in condition identification based on the translation method, condition, language, and prediction model. The accuracy of some models was more affected than others by factors like the conditions\u2019 literature prevalence, language script, family, and language prevalence. Adaptive translation for select languages did not improve translations or diagnostic accuracy with the 3 tested LLMs. However, further analysis with 1 language showed that this approach was more effective with smaller LLMs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>AI-based translation has variable performance, which can affect the ability of AI models to recognize genetic conditions. These findings should inform safe medical AI use to support consistent performance in different languages.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag067","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T11:41:57Z","timestamp":1776253317000},"page":"1284-1292","source":"Crossref","is-referenced-by-count":2,"title":["Disparate language and model effects on AI-based translation and recognition of genetic conditions"],"prefix":"10.1093","volume":"33","author":[{"given":"Dat","family":"Duong","sequence":"first","affiliation":[{"name":"Medical Genetics Branch, National Human Genome Research Institute , Bethesda, Maryland,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irini","family":"Manoli","sequence":"additional","affiliation":[{"name":"Metabolic Medicine Branch, National Human Genome Research Institute , Bethesda, Maryland,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubha R","family":"Phadke","sequence":"additional","affiliation":[{"name":"Medical Genetics, Jupiter Hospital, Baner , Pune,","place":["India"]},{"name":"Medical Genetics, Bharati Vidyapeeth Medical College , Pune,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0130-9101","authenticated-orcid":false,"given":"Chanika","family":"Phornphutkul","sequence":"additional","affiliation":[{"name":"Division of Genetics and Metabolism, Brown University, Providence , Rhode Island,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan D","family":"Raymond","sequence":"additional","affiliation":[{"name":"Medical Genetics Branch, National Human Genome Research Institute , Bethesda, Maryland,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin D","family":"Solomon","sequence":"additional","affiliation":[{"name":"Medical Genetics Branch, National Human Genome Research Institute , Bethesda, Maryland,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2026063015350584600_ocag067-B1","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1038\/s41431-024-01782-w","article-title":"Artificial intelligence in clinical genetics","volume":"33","author":"Duong","year":"2025","journal-title":"Eur J Hum Genet"},{"key":"2026063015350584600_ocag067-B2","doi-asserted-by":"publisher","first-page":"e32061","DOI":"10.1002\/ajmg.c.32061","article-title":"Computational facial analysis for rare Mendelian disorders","volume":"193","author":"Hsieh","year":"2023","journal-title":"Am J Med Genet C Semin Med Genet"},{"key":"2026063015350584600_ocag067-B3","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1016\/j.gim.2022.04.025","article-title":"Scoping review and classification of deep learning in medical genetics","volume":"24","author":"Ledgister Hanchard","year":"2022","journal-title":"Genet Med"},{"key":"2026063015350584600_ocag067-B4","doi-asserted-by":"publisher","first-page":"e32057","DOI":"10.1002\/ajmg.c.32057","article-title":"Applications of artificial intelligence in clinical laboratory genomics","volume":"193","author":"Aradhya","year":"2023","journal-title":"Am J Med Genet C Semin Med Genet"},{"key":"2026063015350584600_ocag067-B5","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1002\/ajmg.c.31866","article-title":"Democratizing genomics: Leveraging software to make genetics an integral part of routine care","volume":"187","author":"Snir","year":"2021","journal-title":"Am J Med Genet C Semin Med Genet"},{"key":"2026063015350584600_ocag067-B6","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2026063015350584600_ocag067-B7","doi-asserted-by":"publisher","first-page":"eadg7492","DOI":"10.1126\/science.adg7492","article-title":"Accurate proteome-wide missense variant effect prediction with AlphaMissense","volume":"381","author":"Cheng","year":"2023","journal-title":"Science"},{"key":"2026063015350584600_ocag067-B8","doi-asserted-by":"publisher","author":"Shyr","year":"2025","DOI":"10.1101\/2025.08.06.25333170"},{"key":"2026063015350584600_ocag067-B9","author":"Raj","year":"2025"},{"key":"2026063015350584600_ocag067-B10","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1016\/j.ajhg.2024.07.011","article-title":"Evaluating large language models on medical, lay language, and self-reported descriptions of genetic conditions","volume":"111","author":"Flaharty","year":"2024","journal-title":"Am J Hum Genet"},{"key":"2026063015350584600_ocag067-B11","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1038\/s41514-025-00226-z","article-title":"Assessing large language model performance related to aging in genetic conditions","volume":"11","author":"Othman","year":"2025","journal-title":"NPJ Aging"},{"key":"2026063015350584600_ocag067-B12","doi-asserted-by":"publisher","first-page":"e63878","DOI":"10.1002\/ajmg.a.63878","article-title":"Diagnostic accuracy of a custom large language model on rare pediatric disease case reports","volume":"197","author":"Young","year":"2025","journal-title":"Am J Med Genet A"},{"key":"2026063015350584600_ocag067-B13","doi-asserted-by":"publisher","first-page":"2271","DOI":"10.1093\/jamia\/ocae128","article-title":"A comparative evaluation of ChatGPT 3.5 and ChatGPT 4 in responses to selected genetics questions","volume":"31","author":"McGrath","year":"2024","journal-title":"J Am Med Inform Assoc"},{"key":"2026063015350584600_ocag067-B14","doi-asserted-by":"publisher","first-page":"105965","DOI":"10.1016\/j.ebiom.2025.105965","article-title":"Development of self-phenotyping tools to empower patients and improve diagnostics","volume":"121","author":"Shefchek","year":"2025","journal-title":"EBioMedicine"},{"key":"2026063015350584600_ocag067-B15","doi-asserted-by":"publisher","first-page":"e64118","DOI":"10.1002\/ajmg.a.64118","article-title":"Perspectives on the current and future state of artificial intelligence in medical genetics","volume":"197","author":"Solomon","year":"2025","journal-title":"Am J Med Genet A"},{"key":"2026063015350584600_ocag067-B16","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.1038\/s41436-021-01162-5","article-title":"The 2019 US medical genetics workforce: a focus on clinical genetics","volume":"23","author":"Jenkins","year":"2021","journal-title":"Genet Med"},{"key":"2026063015350584600_ocag067-B17","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1002\/ajmg.a.61124","article-title":"The burden of rare diseases","volume":"179","author":"Ferreira","year":"2019","journal-title":"Am J Med Genet A"},{"key":"2026063015350584600_ocag067-B18","doi-asserted-by":"publisher","first-page":"e2532312","DOI":"10.1001\/jamanetworkopen.2025.32312","article-title":"Accuracy of artificial intelligence vs professionally translated discharge instructions","volume":"8","author":"Martos","year":"2025","journal-title":"JAMA Netw Open"},{"key":"2026063015350584600_ocag067-B19","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1038\/s41746-025-02055-6","article-title":"Evaluating human-in-the-loop strategies for artificial intelligence-enabled translation of patient discharge instructions: a multidisciplinary analysis","volume":"8","author":"Brewster","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2026063015350584600_ocag067-B20","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1542\/peds.2023-065573","article-title":"Performance of ChatGPT and Google translate for pediatric discharge instruction translation","volume":"154","author":"Brewster","year":"2024","journal-title":"Pediatrics"},{"key":"2026063015350584600_ocag067-B21","doi-asserted-by":"publisher","first-page":"117","DOI":"10.21037\/atm-24-162","article-title":"Artificial intelligence in clinical settings: a systematic review of its role in language translation and interpretation","volume":"12","author":"Genovese","year":"2024","journal-title":"Ann Transl Med"},{"key":"2026063015350584600_ocag067-B22","doi-asserted-by":"publisher","first-page":"105957","DOI":"10.1016\/j.ebiom.2025.105957","article-title":"Consistent performance of large language models in rare disease diagnosis across ten languages and 4917 cases","volume":"121","author":"Chimirri","year":"2025","journal-title":"EBioMedicine"},{"key":"2026063015350584600_ocag067-B23","doi-asserted-by":"publisher","first-page":"1844","DOI":"10.1093\/jamia\/ocae029","article-title":"BioLORD-2023: semantic textual representations fusing large language models and clinical knowledge graph insights","volume":"31","author":"Remy","year":"2024","journal-title":"J Am Med Inform Assoc"},{"key":"2026063015350584600_ocag067-B24","author":"Krikri: Advancing Open Large Language Models for Greek","year":"2025"},{"key":"2026063015350584600_ocag067-B25","author":"Grattafiori","year":"2024"},{"key":"2026063015350584600_ocag067-B26","author":"Christophe","year":"2024"},{"key":"2026063015350584600_ocag067-B27","doi-asserted-by":"publisher","first-page":"e32060","DOI":"10.1002\/ajmg.c.32060","article-title":"Artificial intelligence and the impact on medical genetics","volume":"93","author":"Solomon","year":"2023","journal-title":"Am J Med Genet C Semin Med Genet"},{"key":"2026063015350584600_ocag067-B28","doi-asserted-by":"publisher","first-page":"ooaf054","DOI":"10.1093\/jamiaopen\/ooaf054","article-title":"Reproducible generative artificial intelligence evaluation for health care: a clinician-in-the-loop approach","volume":"8","author":"Livingston","year":"2025","journal-title":"JAMIA Open"},{"key":"2026063015350584600_ocag067-B29","doi-asserted-by":"publisher","first-page":"100558","DOI":"10.1016\/j.xhgg.2025.100558","article-title":"A systematic assessment of large language models\u2019 knowledge of rare diseases: How much do large language models know about rare disease?","volume":"7","author":"Groza","year":"2026","journal-title":"HGG Adv"},{"key":"2026063015350584600_ocag067-B30","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1056\/NEJMsa1507092","article-title":"Genetic misdiagnoses and the potential for health disparities","volume":"375","author":"Manrai","year":"2016","journal-title":"N Engl J Med"},{"key":"2026063015350584600_ocag067-B31","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-4438861\/v1","article-title":"GestaltMatcher database - a global reference for facial phenotypic variability in rare human diseases","author":"Lesmann","year":"2024","journal-title":"Res Sq"},{"key":"2026063015350584600_ocag067-B32","doi-asserted-by":"publisher","first-page":"2939","DOI":"10.1002\/ajmg.a.61888","article-title":"Rubinstein-Taybi syndrome in diverse populations","volume":"182","author":"Tekendo-Ngongang","year":"2020","journal-title":"Am J Med Genet A"},{"key":"2026063015350584600_ocag067-B33","doi-asserted-by":"publisher","first-page":"864092","DOI":"10.3389\/fgene.2022.864092","article-title":"Neural networks for classification and image generation of aging in genetic syndromes","volume":"13","author":"Duong","year":"2022","journal-title":"Front Genet"},{"key":"2026063015350584600_ocag067-B34","doi-asserted-by":"publisher","first-page":"e1011168","DOI":"10.1371\/journal.pgen.1011168","article-title":"Comparison of clinical geneticist and computer visual attention in assessing genetic conditions","volume":"20","author":"Duong","year":"2024","journal-title":"PLoS Genet"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag067\/68231624\/ocag067.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/7\/1284\/68231624\/ocag067.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/7\/1284\/68231624\/ocag067.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T10:33:14Z","timestamp":1782901994000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/7\/1284\/8671285"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":34,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,5,6]]},"published-print":{"date-parts":[[2026,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag067","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,5,6]]}}}